Skip to main content

Using Gen AI to write Kids Books

I have been exploring the variety of options that are available with Gen AI. Not just the different AI tools but the differ things they can be used for. In my day job they can be great for rewriting bits of code or looking up how to do specific tasks in python but the data I work with means I could never ask for anything specific. I am still looking for an interesting home coding project to do but in the meantime I have gotten creative. 

Working with my daughter I have started to create some books for kids. Probably best aimed at around the 6-10 year old mark, they are just fun books with a bit of a laugh in them. The great thing is that it is fairly easy to make the bulk of these books using GenAI which I have also used for cover art and for a bunch of logos and banners for a websites. 

The Website is here and the first book is here (only £0.99 from Amazon). 

The writing process:

Prompt 1: I have idea xyz for a children's book aimed at 6-8 year olds, here is an guide blah blah please write some sections for the book. Note that that might take a few attempts to get the full list of sections and sometimes the sections will need breaking down into chapters. 

Prompt 2: Get the sections / breakdown from the first prompts and plug them into the tools asking for it to write the section. Plug them together. 

Proof Read: The next step is manual but read through the story and check it flows and makes sense. 

Pictures: I used Ideogram to generate my images as it does a better job with text than CoPilot using DALL-E. 



Convert to ePub
: Download as a DOCX and then import into calibre (which is free) and then you can convert it to ePub. There is then a tool to check how things will convert in Kindle. You may have to play around with the contents page to get it to put chapters in correctly. But that probably requires a whole post on its own. 

Overall it is really simple to make a kids picture book using Gen AI and put it on Kindle. I reckon if I put an hours worth of time into it everyday I could easily generate a book a week and once I have a more streamlined process maybe 2. 

So far my daughter has loved both the books I have made and has actually read them both from start to finish. Imagine doing that over 10 years and having circa 1000 books illustrated kids books on Amazon. I mean realistically they aren't going to sell in their thousands but, if you were to make on average 50p profit per sale, and sell 2 of each book a week that is still £1000 a week! 

Comments

Popular posts from this blog

Gen AI news 29-04-2024

Here are some recent updates and insights related to Generative AI (gen AI) : Enterprise Hits and Misses - Robotics and Gen AI Converge : This article discusses the convergence of robotics and generative AI. It explores breakthroughs needed in the field, the FTC’s policy change regarding non-competes, and the impact on AI model sizes for enterprises 1 . Read more All You Need To Know About The Upcoming AI-Powered OLED iPad Pro : This piece provides a summary of rumors surrounding the next-gen AI-fused OLED iPad Pro, powered by the new Apple M4 chip 2 . Read more Delivering on the Promise of Gen AI : New Electronics reflects on NVIDIA GTC and key announcements that contribute to delivering on the promises made for generative AI 3 . Read more The Future of Generative AI - An Early View in 15 Charts (McKinsey): Since the release of ChatGPT in November 2022, generative AI has been making headlines. McKinsey research estimates that gen AI features could add up to $4.4 trillion to the globa...

Keboola Flows

Really finding Keboola was the thing that kickstarted this project otherwise I would be trying to build custom code on a python cloud server and building everything from scratch.  In Keboola you build you data sources and destinations using connection details which is fairly simple and something I will likely cover in another post, same goes for transformations etc. Here though I am going to discuss Flows, this is where you bring everything together. On my free account there are some limitations.  My easiest flow is very basic:  Pull parkrun results e-mail from Gmail to Google Sheets (actually done by Zap not Keboola).  Keboola will, as often as I like, in this case once a week, pull the data from the sheet into its storage.  It will then transfer this to the target database. Currently I have this setup to be MySQL database but I can and might expand that to the Snowflake instance within Keboola.  I then, outside of Keboola, connect to the MySQL database f...

Snowflake Scripting - SQL Cursors

Snowflake scripting in SQL seems to be in preview and I have decided to have a play with it. Given how new it is there is limited documentation so I am using a combination of what I can find on the Snowflake site and the odd blog that has been written about it. There appear to be a few quirks, at least when compared to Oracle PL/SQL (though that has been round for years). How many of these are intentional and how many are things to be ironed out I don't know. You can see the procedure I have created it:  Accepts an id as a parameter  Creates a result set selecting from a table, using the parameter as a filter Loads the results set into a cursor.  Loops through the cursor loading the id in the cursor into variable Calls procedure passing in the variable as the parameter.  Then as a proof of concept I tried the Snowflake feature of allowing declaration of variables within the main start and end block.